Drew Breunig · 2026-08-23 · notable
Drew Breunig — expensive models ended the free lunch in AI coding
Drew Breunig argues that Claude Fable 5 broke the habit of waiting for a cheaper model to solve your problems. He now sends design work to Fable and rote coding to GLM 5.2, which he puts at about one-ninth of Fable's cost.
Drew Breunig argues that Claude Fable 5's price ended the habit of waiting for a cheaper model to fix your code.
What is it?
The free lunch in AI coding is over, Drew Breunig argues in this essay, because a new model no longer arrives at the same price and papers over your problems. He borrows the phrase from Herb Sutter, who used it for the years when Moore's Law doubled single-thread CPU speed and made careful optimization look like wasted effort. Breunig says Claude Fable 5 is the model that broke the pattern: it is excellent, but costly enough that developers had to start asking what work goes where.
How does it work?
The routing habit Breunig describes splits one task across two models. He chats with Claude Fable 5 to interrogate and shape a design, then hands a written brief to GLM 5.2 for the rote coding. GLM 5.2 shipped the same week as Fable at roughly one-ninth of its cost and about one-fifth the cost of Opus 5, and Breunig says it is more than sufficient for most routine work when it is given good context.
Why does it matter?
The common objection is that falling inference prices will eventually push everything back through the biggest model. Breunig doubts it: the same price gains reach Kimi K3 and Qwen too, and better harnesses keep making it easier to feed a weaker model enough context to do well. He adds that Claude Fable 5's access controls, dynamic degradation, and required data retention pushed companies and countries to think about where their traces go, which he expects will lock the multi-model habit in.
Who is it for?
developers picking which model gets which task